On the Binding Mechanism of Synchronised Visual Events

Authors:
Jeffrey Ng;Shaogang Gong
Affiliations:
-;-
Venue:
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
Year:
2002

Citing 0
Cited 3

Synchronization of oscillations for machine perception of gaits

Computer Vision and Image Understanding
Spatial Models for Wide-Area Visual Surveillance: Computational Approaches and Spatial Building-Blocks

Artificial Intelligence Review
Synchronization of oscillations for machine perception of gaits

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of interpreting visual surveil-lancedata by learning appropriate spatio-temporal sub-spacesof active image regions caused by scene activities.We focus on identifying regions of sustained change forrecognising key stages of a visual behaviour. Our behaviourrepresentation is based on the asynchrony or delay patternsof occurrence among local events which need notbe spatially connected. We use an automatic NormalisedCut structure discovery algorithm with a hybrid similaritycriteria for simultaneously identifying relevant spatio-temporalsubspaces and clustering similar behaviour pat-ternsin those subspaces. We compare the automaticallydiscovered classes with conceptual classes of behaviours ina semi-constrained "Shopping" scenario.